add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"n": 1, "b": 2, "i": 3, "e": 4, "v": 5, "k": 6, "t": 7, "f": 8, "d": 9, "h": 10, "p": 11, "a": 12, "j": 13, "c": 14, "z": 15, "o": 16, "y": 17, "r": 18, "s": 19, "l": 20, "q": 21, "w": 22, "m": 23, "x": 24, "g": 25, "u": 26, "|": 0, "[UNK]": 27, "[PAD]": 28}